blumeops/mise-tasks/docs-review

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.12"
# dependencies = ["pyyaml==6.0.3", "rich==15.0.0", "typer==0.26.2"]
# ///
#MISE description="Review the most stale documentation card by last-reviewed date"
#USAGE flag "--limit <limit>" default="15" help="Number of docs to show in the table"
"""Review the most stale documentation card by last-reviewed date.

Scans all markdown files in docs/ (excluding changelog.d/) and sorts them
by the ``last-reviewed`` frontmatter field, with git last-modified date as
a tiebreaker (least recently updated first). Docs without the field are
treated as never-reviewed and float to the top. Displays a staleness
table and then shows the most stale doc with a review checklist.

After reviewing, update the card's frontmatter:

    last-reviewed: YYYY-MM-DD

Usage: mise run docs-review [-- --limit 10]
"""

import subprocess
import sys
from datetime import date, datetime, timezone
from pathlib import Path
from typing import Annotated

import typer
import yaml
from rich.console import Console
from rich.markdown import Markdown
from rich.panel import Panel
from rich.table import Table

DOCS_DIR = Path(__file__).parent.parent / "docs"


def extract_frontmatter(file_path: Path) -> dict | None:
    """Extract YAML frontmatter from a markdown file."""
    content = file_path.read_text()
    if not content.startswith("---"):
        return None

    end_idx = content.find("---", 3)
    if end_idx == -1:
        return None

    frontmatter_text = content[3:end_idx].strip()
    try:
        return yaml.safe_load(frontmatter_text) or {}
    except yaml.YAMLError:
        return None


def get_last_reviewed(frontmatter: dict) -> date | None:
    """Extract last-reviewed date from frontmatter."""
    raw = frontmatter.get("last-reviewed")
    if raw is None:
        return None
    if isinstance(raw, date):
        return raw
    try:
        return date.fromisoformat(str(raw))
    except ValueError:
        return None


def git_last_modified(file_path: Path) -> datetime | None:
    """Get the last git commit date for a file."""
    try:
        result = subprocess.run(
            ["git", "log", "-1", "--format=%aI", "--", str(file_path)],
            capture_output=True,
            text=True,
            check=True,
        )
        date_str = result.stdout.strip()
        if not date_str:
            return None
        return datetime.fromisoformat(date_str)
    except subprocess.CalledProcessError:
        return None


def main(
    limit: Annotated[int, typer.Option(help="Number of docs to show in the table")] = 15,
) -> None:
    console = Console()
    today = date.today()

    entries: list[tuple[str, date | None, datetime | None, Path]] = []

    for md_file in sorted(DOCS_DIR.rglob("*.md")):
        if "changelog.d" in md_file.parts:
            continue

        frontmatter = extract_frontmatter(md_file)
        last_reviewed = get_last_reviewed(frontmatter) if frontmatter else None
        last_updated = git_last_modified(md_file)
        rel_path = str(md_file.relative_to(DOCS_DIR))
        entries.append((rel_path, last_reviewed, last_updated, md_file))

    # Sort: never-reviewed first (None), then oldest reviewed,
    # then least recently updated as tiebreaker
    entries.sort(key=lambda e: (
        e[1] is not None,
        e[1] or date.min,
        e[2] or datetime.min.replace(tzinfo=timezone.utc),
    ))

    never_reviewed = sum(1 for e in entries if e[1] is None)

    # --- Staleness table ---
    console.print()
    console.print(Panel(
        f"[bold]{len(entries)}[/bold] total docs, "
        f"[bold red]{never_reviewed}[/bold red] never reviewed",
        title="[bold]Documentation Review Queue[/bold]",
        border_style="cyan",
    ))
    console.print()

    table = Table(show_header=True, header_style="bold")
    table.add_column("#", justify="right")
    table.add_column("File")
    table.add_column("Last Reviewed", justify="right")
    table.add_column("Age (days)", justify="right")
    table.add_column("Last Updated", justify="right")

    for i, (rel_path, last_reviewed, last_updated, _) in enumerate(entries[:limit], 1):
        updated_str = last_updated.strftime("%Y-%m-%d") if last_updated else "?"
        if last_reviewed is None:
            table.add_row(
                str(i),
                f"[red]{rel_path}[/red]",
                "[red]never[/red]",
                "[red]—[/red]",
                updated_str,
            )
        else:
            age = (today - last_reviewed).days
            style = "yellow" if age > 90 else ""
            age_str = f"[{style}]{age}[/{style}]" if style else str(age)
            path_str = f"[{style}]{rel_path}[/{style}]" if style else rel_path
            date_str = f"[{style}]{last_reviewed}[/{style}]" if style else str(last_reviewed)
            table.add_row(str(i), path_str, date_str, age_str, updated_str)

    remaining = len(entries) - limit
    if remaining > 0:
        table.add_row("", f"[dim]… {remaining} more[/dim]", "", "", "")

    console.print(table)
    console.print()

    # --- Show the most stale doc ---
    if not entries:
        console.print("[bold red]No documentation files found![/bold red]")
        raise typer.Exit(code=1)

    top_path, top_reviewed, _, top_file = entries[0]
    console.print(Panel(
        f"[bold cyan]{top_path}[/bold cyan]\n"
        + (f"[dim]Last reviewed: {top_reviewed}[/dim]" if top_reviewed else "[dim red]Never reviewed[/dim red]"),
        title="[bold]Up For Review[/bold]",
        border_style="green",
    ))
    console.print()

    console.print(f"[bold]Read the file:[/bold] {top_file.resolve()}")
    console.print()

    console.print()
    console.print(Panel(
        "[bold]Review Checklist:[/bold]\n\n"
        "• Is the information accurate and up-to-date?\n"
        "• Are there broken or missing wiki-links?\n"
        "• Should this card link to other related cards?\n"
        "• Is the card too large and should be split?\n"
        "• Is the card too small and should be merged?\n"
        "• Does the frontmatter (tags, title) make sense?\n"
        "• Is the card in the correct category (reference/how-to/etc)?\n\n"
        "[bold]Verify Deployed State:[/bold]\n\n"
        "• If ArgoCD app: is it synced? (argocd app get <app>)\n"
        "• If Ansible role: does it apply idempotently? (--check --diff)\n"
        "• If Pulumi: is there drift? (pulumi preview)\n\n"
        "[bold]After Review:[/bold]\n\n"
        "• Update the card's frontmatter: [cyan]last-reviewed: "
        + str(today)
        + "[/cyan]\n"
        "• Commit the change (along with any fixes)\n"
        "• User: run [cyan]mise run docs-preview <card-path>[/cyan] for a rendered visual check",
        title="[bold yellow]Review Guidance[/bold yellow]",
        border_style="yellow",
    ))


if __name__ == "__main__":
    typer.run(main)